def webuse(data, baseurl='http://www.stata-press.com/data/r11/', as_df=True):
"""
Parameters
----------
data : str
Name of dataset to fetch.
baseurl : str
The base URL to the stata datasets.
as_df : bool
If True, returns a `pandas.DataFrame`
Returns
-------
dta : Record Array
A record array containing the Stata dataset.
Examples
--------
>>> dta = webuse('auto')
Notes
-----
Make sure baseurl has trailing forward slash. Doesn't do any
error checking in response URLs.
"""
# lazy imports
from statsmodels.iolib import genfromdta
url = urljoin(baseurl, data+'.dta')
dta = urlopen(url)
dta = StringIO(dta.read()) # make it truly file-like
if as_df: # could make this faster if we don't process dta twice?
return DataFrame.from_records(genfromdta(dta))
else:
return genfromdta(dta)
def get_griliches76_data():
import os
curdir = os.path.split(__file__)[0]
path = os.path.join(curdir, 'griliches76.dta')
griliches76_data = iolib.genfromdta(path, missing_flt=np.NaN, pandas=True)
# create year dummies
years = griliches76_data['year'].unique()
N = griliches76_data.shape[0]
for yr in years:
griliches76_data['D_%i' % yr] = np.zeros(N)
for i in range(N):
if griliches76_data.loc[griliches76_data.index[i], 'year'] == yr:
griliches76_data.loc[griliches76_data.index[i],
'D_%i' % yr] = 1
else:
pass
griliches76_data['const'] = 1
X = add_constant(griliches76_data[[
's', 'iq', 'expr', 'tenure', 'rns', 'smsa', 'D_67', 'D_68', 'D_69',
'D_70', 'D_71', 'D_73'
]],
prepend=True) # for R comparison
#prepend=False) # for Stata comparison
Z = add_constant(griliches76_data[['expr', 'tenure', 'rns', 'smsa', \
'D_67', 'D_68', 'D_69', 'D_70', 'D_71',
'D_73', 'med', 'kww', 'age', 'mrt']])
Y = griliches76_data['lw']
return Y, X, Z
def webuse(data, baseurl='http://www.stata-press.com/data/r11/'):
"""
Parameters
----------
data : str
Name of dataset to fetch.
Returns
-------
dta : Record Array
A record array containing the Stata dataset.
Examples
--------
>>> dta = webuse('auto')
Notes
-----
Make sure baseurl has trailing forward slash. Doesn't do any
error checking in response URLs.
"""
# lazy imports
import pandas
from statsmodels.iolib import genfromdta
from urllib2 import urlopen
from urlparse import urljoin
from StringIO import StringIO
url = urljoin(baseurl, data+'.dta')
dta = urlopen(url)
dta = StringIO(dta.read()) # make it truly file-like
return genfromdta(dta)
def get_griliches76_data():
import os
curdir = os.path.split(__file__)[0]
path = os.path.join(curdir, 'griliches76.dta')
griliches76_data = iolib.genfromdta(path, missing_flt=np.NaN, pandas=True)
# create year dummies
years = griliches76_data['year'].unique()
N = griliches76_data.shape[0]
for yr in years:
griliches76_data['D_%i' %yr] = np.zeros(N)
for i in range(N):
if griliches76_data.ix[i, 'year'] == yr:
griliches76_data.ix[i, 'D_%i' %yr] = 1
else:
pass
griliches76_data['const'] = 1
X = add_constant(griliches76_data[['s', 'iq', 'expr', 'tenure', 'rns',
'smsa', 'D_67', 'D_68', 'D_69', 'D_70',
'D_71', 'D_73']],
prepend=True) # for R comparison
#prepend=False) # for Stata comparison
Z = add_constant(griliches76_data[['expr', 'tenure', 'rns', 'smsa', \
'D_67', 'D_68', 'D_69', 'D_70', 'D_71',
'D_73', 'med', 'kww', 'age', 'mrt']])
Y = griliches76_data['lw']
return Y, X, Z
def webuse(data, baseurl='http://www.stata-press.com/data/r11/'):
"""
Parameters
----------
data : str
Name of dataset to fetch.
Returns
-------
dta : Record Array
A record array containing the Stata dataset.
Examples
--------
>>> dta = webuse('auto')
Notes
-----
Make sure baseurl has trailing forward slash. Doesn't do any
error checking in response URLs.
"""
# lazy imports
import pandas
from statsmodels.iolib import genfromdta
from urllib2 import urlopen
from urlparse import urljoin
from StringIO import StringIO
url = urljoin(baseurl, data+'.dta')
dta = urlopen(url)
dta = StringIO(dta.read()) # make it truly file-like
return genfromdta(dta)
